statsmodels.tsa.forecasting.theta.ThetaModelResults.forecast

ThetaModelResults.forecast(steps=1, theta=2)

Forecast the model for a given theta

Parameters:

stepsint

The number of steps ahead to compute the forecast components.

thetafloat

The theta value to use when computing the weight to combine the trend and the SES forecasts.

Returns:

Series

A Series containing the forecasts

Notes

The forecast is computed as

$${\hat{X}}_{T+h|T}=\frac{\theta -1}{\theta }{b}_0[h-1+\frac{1}{\alpha }-\frac{(1-\alpha {)}^T}{\alpha }]+{\tilde{X}}_{T+h|T}$$

where ${\tilde{X}}_{T+h|T}$ is the SES forecast of the endogenous variable using the parameter $\alpha$. $b_0$ is the slope of a time trend line fitted to X using the terms 0, 1, …, T-1.

This expression follows from [1] and [2] when the combination weights are restricted to be (theta-1)/theta and 1/theta. This nests the original implementation when theta=2 and the two weights are both 1/2.

References

[1]

Hyndman, R. J., & Billah, B. (2003). Unmasking the Theta method. International Journal of Forecasting, 19(2), 287-290.

[2]

Fioruci, J. A., Pellegrini, T. R., Louzada, F., & Petropoulos, F. (2015). The optimized theta method. arXiv preprint arXiv:1503.03529.